The present invention relates to determining remaining life of a bearing in a technical system.

Bearings may be subject to currents that are caused by drives that are used to drive low voltage and medium voltage tech nical systems. The currents in the bearing may lead to several kinds of damage such as current based erosion. The current erosion may further lead to fatigue crack propagation in bear ing raceways. The damage reduces life of the bearings. The re duced life of the bearings may lead to failure of the tech nical systems that include the bearings .

To overcome damage of the bearings, methods to protect the bearings have been used. The methods include insulation of the bearing, usage of shaft grounding brush, conductive greases etc. Such methods may be expensive and in-effective in esti mating remaining life of the bearings.

In light of the above, there exists a need to determine re maining life of a bearing.

Therefore, it is an object of the present invention to provide a system, apparatus and method for determine remaining life of a bearing in a technical system.

The object of the present invention is achieved by a method to determine remaining life of the bearing in the technical sys tem. The method comprises generating a bearing model of the bearing. As used herein, the bearing model is digital repre sentation of the bearing based on condition data associated with operation of the bearing, historical condition data of the bearing, bearing specification and technical specification of the technical system. For example, the bearing model repre sents operating conditions of the bearing in real-time and the historical operating conditions of the bearing. The condition data of the bearing is received from different sources (e.g., sensors, scanners, user devices, etc.)· The sensors measure operating parameters associated with the tech nical system. The sensors may include vibration sensors, cur rent and voltage sensors, etc. For example, measurement of shaft voltage in a motor is mapped to an operation parameter of the bearing. The term "operation parameter" refers to one or more characteristics of the bearing. Accordingly, the con dition data is a measure of the operating parameters associat ed with the operation of the bearing. For example, the condi tion data includes values of vibration, temperature, current, magnetic flux, velocity, power of the motor including the bearing .

The method may comprise generating a voltage model of the bearing based on the condition data. The condition data in cludes bearing load and bearing speed. In an embodiment, the bearing load and bearing speed is mapped with respect to breakdown voltage of the bearing and a common mode voltage of the bearing. In another embodiment, the bearing load and bear ing speed are mapped in a graphical programming environment . The advantage of mapping the bearing load and bearing speed enables modelling, simulation and analysis of multidomain dy namical systems .

The method may comprise converting an alternating voltage in put to the technical system to a Pulse Width Modulated (PWM) output. For example, the technical system is a three phase Al ternating Current (AC) induction motor that are driven by Var iable Frequency Drives (VFD) . The alternating voltage input to the AC induction motor is converted to PWM output.

Further, the method may comprise determining whether the PWM output is within a predetermined voltage threshold. Consider ing the example of the AC induction motor, sum of three phases of PWM output must ideally be zero. According, it is deter mined whether the PWM output is within zero or in a tolerance range of zero. Furthermore, the method may comprise determining the breakdown voltage and the common mode voltage based on deviation from the predetermined voltage threshold. In case of the AC induc tion motor, if the sum of the three phases of PWM output does not add to zero. The deviation from zero is used to determine the common mode voltage.

The method may comprise generating a current model of the bearing based on the voltage model, the bearing specification and the technical specification. The current model maps the breakdown voltage and the common mode voltage to discharge current. For example, the bearing specification includes bear ing dimensions, bearing size, bearing lubrication, lubrication thickness, bearing operating temperature, bearing interfaces, etc. The technical specification includes technical system type, technical system load, technical system speed, technical system orientation, etc.

In an embodiment, the method may comprise generating an equiv alent circuit with the bearing specification and the technical specification. For example, the equivalent circuit of the AC induction motor is represented in relation to the capacitanc es, inductances and resistances of winding, frame, etc of the AC induction motor. The method may further comprise, applying the common mode voltage as input to the equivalent circuit . The equivalent circuit outputs shaft-ground voltage in re sponse to the common mode voltage. The current model is gener ated based on the shaft ground voltage. As used herein, the current model includes values of the discharge current in time series with respect to the shaft ground voltage and the common mode voltage. In addition, the method may comprise mapping the lubricant thickness as a function of the technical system load and the technical system speed.

The method may comprise generating a spark heat based on the current model for at least one spark. Further, determining a spark diameter based on the current model. The method may fur ther comprise determining a thermal model based on the current model. As used herein, the thermal model is a representation of the spark heat and the spark diameter. The thermal model maps the spark heat and the spark diameter to the discharge current. In an embodiment, the thermal model includes distri bution of the spark heat and the spark diameter in time se ries .

The method may comprise determining radius and peaks of the discharge current in the current model. The spark heat for a bearing surface of the bearing is determined based on the ra dius and peaks of discharge current. In an embodiment, the method may comprise generating the thermal model by mapping the spark heat and the spark diameter with the discharge cur rent. In another embodiment, the thermal model is generated by mapping the spark heat and the spark diameter to surface points on the bearing surface.

The method comprises predicting a defect in the bearing based on the bearing model. The defect in the bearing may include erosion of bearing raceway due to the discharge current. The method is advantageous as the defect is determined based on a combination of condition data associated with operation of the bearing, historical condition data of the bearing, bearing specification and technical specification of the technical system.

The method may comprise comparing the condition data with de fect profiles. As used herein, the term "defect profile" re fers to anomalous data represented as a function of operation environment, operation profile and/or load profile associated with the bearing and/or technical system.

The defect profiles are generated based on the bearing speci fication and the technical specification. The defect in the bearing may also be predicted based on the comparison between the condition data and with predetermined defect profiles. In an embodiment, the method may comprise generating a defect model including the defect profiles that are generated from a bearing fleet and a fleet of the technical system. The method is advantageous as the defect profiles are used to determine erosion pattern on the bearing surface. The erosion pattern is indicative of the defect such as defect type, defect location, defect severity, etc.

In an embodiment, the method may comprise determining a bear ing current in real-time. The bearing current is input to the thermal model to determine the one which does real time cur rent measurement. This current can be used as an input to the thermal model to generate the erosion pattern.

In another embodiment, the method may comprise determining lo cation of the at least one spark in the bearing. For example, the location of spark in the bearing raceway is determined. Further, the thermal model is generated for multiple thermal loads of the bearing. The thermal model is analysed to identi fy vaporization temperature. For example, the vaporization temperature of the bearing lubrication is determined. The va porization temperature is used to determine the erosion pat tern .

The method comprises predicting remaining life of the bearing based on the predicted defect. In an embodiment, the remaining life of the bearing is predicted based on the defect profiles and/or the erosion pattern. For example, the defect profiles are associated with predetermined life profiles. The predeter mined life profiles are learned from the historical condition data of the bearing or the fleet of bearings. Example learning techniques include supervised and/or unsupervised learning techniques such as reinforced learning, deep reinforced learn ing, k-means clustering, etc.

The method may comprise predicting a defect propagation based on location of the defect and type of the defect. Further, the remaining life of the bearing based on the predicted defect propagation. As used herein, the remaining life refers to life of the bearing with and without the detected defect . The re maining life includes remaining useful life (RUL) , down-time, maintenance time, etc. The method may comprise estimating an expended life of the bearing based on the bearing model. The remaining life is es timated based on the expended life and first detection anomaly in the condition data. The method may comprise rendering the expended life, the remaining life and a usage profile of the bearing. The method may further comprise rendering a degrada tion view of the bearing and/or the technical system based on the bearing model. The degradation view depicts a real-time degradation and a predicted degradation of the bearing or the technical system. The real-time degradation is determined based on vibration data from the condition data. The method advantageously depicts the impact of the defect in the bearing in terms of degradation of the technical system.

The object of the present invention is achieved by an appa ratus for for determining remaining life of a bearing in a technical system. The apparatus comprising one or more pro cessing units and a memory unit communicative coupled to the one or more processing units, wherein the memory unit compris es a bearing module stored in the form of machine-readable in structions executable by the one or more processing units, wherein the bearing module is configured to perform one or more method steps described above. The execution of the bear ing module can also be performed using co-processors such as Graphical Processing Unit (GPU) , Field Programmable Gate Array (FPGA) or Neural Processing/Compute Engines.

According to an embodiment of the present invention, the appa ratus can be an edge computing device. As used herein "edge computing" refers to computing environment that is capable of being performed on an edge device (e.g., connected to the sen sors unit in an industrial setup and one end and to a remote server (s) such as for computing server (s) or cloud computing server (s) on other end), which may be a compact computing de vice that has a small form factor and resource constraints in terms of computing power. A network of the edge computing de vices can also be used to implement the apparatus. Such a net work of edge computing devices is referred to as a fog net work . In another embodiment, the apparatus is a cloud computing sys tem having a cloud computing based platform configured to pro vide a cloud service for analyzing condition data of the bear ing and/or the technical system. As used herein, "cloud compu ting" refers to a processing environment comprising configura ble computing physical and logical resources, for example, networks, servers, storage, applications, services, etc., and data distributed over the network, for example, the internet. The cloud computing system provides on-demand network access to a shared pool of the configurable computing physical and logical resources. The network is, for example, a wired net work, a wireless network, a communication network, or a net work formed from any combination of these networks.

Additionally, the object of the present invention is achieved by a system comprising one or more devices capable of provid ing condition data associated with operation of one or more technical systems in a plurality of facilities. The system al so comprises an apparatus, communicatively coupled to the one or more devices, wherein the apparatus is configured for de termining remaining life of at least one bearing in one or more technical systems .

The object of the present invention is achieved by a computer- program product having machine-readable instructions stored therein, which when executed by a processor, cause the proces sor to perform a method as describe above.

The above-mentioned and other features of the invention will now be addressed with reference to the accompanying drawings of the present invention. The illustrated embodiments are intended to illustrate, but not limit the invention.

The present invention is further described hereinafter with reference to illustrated embodiments shown in the accompanying drawings, in which: FIG 1 illustrates a block diagram of a bearing model for a bearing, according an embodiment of the present in vention;

FIG 2 illustrates determination of an erosion pattern from the bearing model, according an embodiment of the present invention;

FIG 3 illustrates a block diagram of an apparatus for de termining remaining life of a bearing, according an embodiment of the present invention;

FIG 4 illustrates a system to manage one or more technical systems with one or more bearings, according an em bodiment of the present invention;

FIG 5 illustrates a system for determining remaining life of a bearing in a technical system, according to an embodiment of the present invention; and

FIG 6 illustrates a method for determining remaining life of a bearing, according to an embodiment of the pre sent invention.

Hereinafter, embodiments for carrying out the present inven tion are described in detail. The various embodiments are de scribed with reference to the drawings, wherein like reference numerals are used to refer to like elements throughout. In the following description, for purpose of explanation, numerous specific details are set forth in order to provide a thorough understanding of one or more embodiments. It may be evident that such embodiments may be practiced without these specific details .

FIG 1 illustrates a block diagram of a bearing model 100 for a bearing in a technical system. The bearing model 100 is gener ated using condition data 102 associated with the bearing and the technical system. The condition data 102 includes bearing load, bearing speed, etc. The bearing model 100 is also gener- ated using historical condition data 104 associated with the bearing and the techincal system. Further, the bearing model 100 is generated using bearing specification 106 and technical specification 108. Accordingly, the condition data 102, the historical condition data 104, the bearing specification 106 and the technical specification 108 are indicated as inputs to the bearing model 100.

The bearing model 100 includes voltage model 110, current mod el 120, thermal model 130, defect model 140. The voltage model 110, current model 120, thermal model 130 and defect model 140 are implemented in one of a one-dimension model, mathematical model and a three-dimension model. The bearing model 100 ad- vantagously integrates the different implementation models. An output of the bearing model 100 is used to perform the steps 152-160 to determine the remaining life of the bearing at step 170.

The voltage model 110 includes a breakdown voltage model 112 and a common mode voltage model 114. The voltage model 110 of the bearing is based on the condition data. In FIG 1, the bearing load and bearing speed is mapped with respect to breakdown voltage of the bearing by the breakdown voltage mod el 112. Further, a common mode voltage of the bearing is mod elled based on the bearing load and bearing speed by the com mon mode voltage model 114.

The current model 120 of the bearing based on the voltage mod el 110, the bearing specification 106 and the technical speci fication 108. For example, the bearing specification includes bearing dimensions, bearing size, bearing lubrication, lubri cation thickness, bearing operating temperature, bearing in terfaces, etc. The technical specification includes technical system type, technical system load, technical system speed, technical system orientation, etc. The current model 120 maps the breakdown voltage and the common mode voltage to discharge current . The current model 120 includes equivalent circuit model 122 generated based on the bearing specification and the technical specification. Further, the common mode voltage as input to the equivalent circuit. The equivalent circuit outputs shaft- ground voltage in response to the common mode voltage. The current model 120 is generated based on the shaft ground volt age. Further, the current model 120 includes a discharge cur rent model 124. The discharge current model 124 includes val ues of the discharge current in time series with respect to the shaft ground voltage and the common mode voltage.

The thermal model 130 includes a heat model 132 based on the current model 120. The heat model 132 is a distribution of spark heat of at least one spark in time series. The at least one spark is determined based on radius and peaks of the dis charge current from the current model 120.

The thermal model 130 includes a radius model 134 of the at least one spark. The radius model 134 determines radius of the at least one spark based on the discharge current. The thermal model 130 also includes a location model 136 determines spark location by mapping the spark heat and the spark diameter to surface points on the bearing.

The defect model 140 includes a defect profile model 142. The defect profile model 142 is configured to map the spark heat and the spark diameter to defect profiles. The defect profiles output from the bearing model 100 and used to determine the remaining life of the bearing at step 170.

Further, the defect profiles are validated by performing steps 152-160. At step 152, the bearing specification and the tech nical specification are used to generated predetermined defect profiles. The bearing specification and the technical specifi cation includes Computer Aided Drawings and multi-physics mod els of the bearing and the technical system.

At step 154, the predetermined defect profiles are mapped to defect locations on the bearing. Further, at step 156 the con- dition data 102 from the bearing is provided to update the predetermined defect profiles with real-time operating condi tions associated with the bearing. At step 158, the defect profile 142 generated from the bearing model 100 is compared with the predetermined defect profiles to validate the spark location. At step 160, an erosion pattern is determined based on the bearing model 100 and the predetermined defect pro files. The erosion pattern is updated in the bearing specifi cation and the technical specification to improve detection of defects in a fleet of the bearing.

FIG 2 illustrates determination of an erosion pattern 250 from the bearing model 100, according an embodiment of the present invention. The thermal model 130 of the bearing model 100 is used to determine the erosion pattern 250. The thermal model 130 the spark heat and spark diameter distribution depicted by the graph 200.

As shown in graph 200, peak of the spark heat is depicted as peak range 202 in the range of 4800°C-5000°C . The distribution of the spark heat reduces to high range 204 in the range of 4200°C-4800°C . The erosion pattern 250 is depicted in between the high range 204 and medium-high range 206. The medium-high range 206 is in the range of 3700°C-4200°C . In addition, the spark heat is also distributed in lower-medium range 208 and lower range 210. In an embodiment, the spark heat distribution is averaged to determine the spark diameter and alse the ero sion pattern.

FIG 3 illustrates a block diagram of an apparatus 300 for de termining remaining life of a bearing 390 in a technical sys tem 380, according an embodiment of the present invention. The bearing 390 in the technical system 380 includes an outer ring 392, a ball 394 and an inner ring 396. The ball 394 runs on a bearing raceway (not shown in FIG 3) .

The technical system 380 is associated multiple sensors 385 that measure operation parameters of the technical system 380. The term "operation parameter" refers to one or more charac- teristics of the technical system. For example, if a motor in an electric vehicle is the technical system, the operation pa rameters include vibration frequency, vibration amplitude, en gine temperature, etc. In an embodiment, the sensors 385 may be provided external to the technical system 380. The sensors 385 may be configured to communicate to the network interface 350 directly.

Further, the technical system 380 includes a trans-receiver 382, a controller 384 and a capable of connecting to a network interface 350. The technical system 380 may also include a Graphical User Interface (GUI) 386 to enable user or service personnel to operate the technical system 380.

In an embodiment, the controller 384 receives sensor data from the sensors 385 and transmits the sensor data to the apparatus 300 via the network interface 350. In another embodiment, the controller 384 performs the functions of the apparatus 300. The controller 384 may comprise a processor and a memory com prising modules in the apparatus 300, specifically bearing module 315.

The apparatus 300 includes a communication unit 302, at least one processor 304, a display 306, a Graphical User Interface (GUI) 308 and a memory 310 communicatively coupled to each other. The communication unit 302 includes a transmitter, a receiver and Gigabit Ethernet port. The memory 310 may include 2 Giga byte Random Access Memory (RAM) Package on Package (PoP) stacked and Flash Storage. The memory 310 is provided with modules stored in the form of computer readable instruc tions, for example, the bearing module 315. The processor 304 is configured to execute the defined computer program instruc tions in the modules. Further, the processor 302 is configured to execute the instructions in the memory 310 simultaneously. The display 306 includes a High-Definition Multimedia Inter face (HDMI ) display 306 and a cooling fan (not shown in the figure) . According to an embodiment of the present invention, the appa ratus 300 is configured on a cloud computing platform imple mented as a service for analyzing data. Additionally, control personnel can access the apparatus 300 via the GUI 308. The GUI 308 is, for example, an online web interface, a web based downloadable application interface, etc.

The memory includes the bearing module 315 that includes a model generator module 320, a defect module 330 and a life module 340. The model generator module 320 is configured to generate a bearing model for the bearing 390. The model gener ator module 320 includes a voltage module 322, a current mod ule 324 and a thermal module 326.

The voltage module 322 generates voltage model for the bearing 390. The voltage module 322 is configured to convert an alter nating voltage input to the technical system 380 to a Pulse Width Modulated (PWM) output. For example, the technical sys tem 390 is a three phase Alternating Current (AC) induction motor that are driven by Variable Frequency Drives (VFD) . The alternating voltage input to the AC induction motor is con verted to PWM output .

Further, the voltage module 322 is configured to determine whether the PWM output is within a predetermined voltage threshold. In the technical system 380 such as the AC induc tion motor, sum of three phases of PWM output must ideally be zero. Accordingly, it is determined whether the PWM output is within zero or in a tolerance range of zero.

Furthermore, the voltage module 322 is configured to the breakdown voltage and the common mode voltage based on devia tion from the predetermined voltage threshold. In case of the AC induction motor, if the sum of the three phases of PWM out put does not add to zero. The deviation from zero is used to determine the common mode voltage.

The current module 324 generates a current model of the bear ing 380. The current module 324 is configured to map the breakdown voltage and the common mode voltage to discharge current. For example, the bearing specification includes bear ing dimensions, bearing size, bearing lubrication, lubrication thickness, bearing operating temperature, bearing interfaces, etc. The technical specification includes technical system type, technical system load, technical system speed, technical system orientation, etc.

The current module 324 is configured to generate an equivalent circuit with bearing specification and technical specification of the bearing 390 and the technical system 380. For example, the equivalent circuit of the AC induction motor is represent ed in relation to the capacitances, inductances and resistanc es of winding, frame, etc of the AC induction motor.

The current model is generated by applying the common mode voltage as input to the equivalent circuit . The equivalent circuit outputs shaft-ground voltage in response to the common mode voltage. The current model is generated based on the shaft ground voltage. As used herein, the current model in cludes values of the discharge current in time series with re spect to the shaft ground voltage and the common mode voltage.

In addition, the current module 324 is configured to map lub ricant thickness of the bearing 390 as a function of load and speed the technical system 380. For example, the lubricant thickness is determined by analysing various lubricant thick ness in terms of the load and speed. The lubricant thickness is measured by

2.69 * G ^0A9 * t/ ₀ ⁰ · ⁶⁸

Ho (1— 0.61 * e ^~ °- ^73x )

W° ⁰⁶⁷

With

Where

a _p is pressure coefficient of viscosity of lubricant in the bearing 390

E Reduced elasticity modulus of the lubricant in the bearing

390

P Load of from contact with the bearing 390 and components in the technical system 390

R _x Radius of curvature in motion plane of the ball 394 in the bearing 390

ho Central lubricant thickness of the lubricant in the bearing 390

R Radius of curvature of the ball 394 in the bearing 390

u Speed of the bearing 390

h ₀ Dynamic oil viscosity of the lubricant in the bearing 390

The thermal module 326 is configured to generate the thermal model of the bearing 390 based on the current model. The ther mal module 326 is configured to determine spark heat based on the current model for at least one spark. The at least one spark is identified based on peak and radius of the discharge current determined in the current model.

Further, the thermal module 326 is configured to determine a spark diameter based on the current model. As used herein, the thermal model is a representation of the spark heat and the spark diameter. The thermal model maps the spark heat and the spark diameter to the discharge current. In an embodiment, the thermal model includes distribution of the spark heat and the spark diameter in time series.

In an embodiment, the thermal module 326 is configured to gen erate the distribution of the spark heat by determining Gauss ian heat flux distribution of the at least one spark. For exa mple, the spark heat distribution is determined by

Where

R _w is energy partion ratio U _b is the breakdown voltage of the bearing 390

/ is the current in the bearing 390

R is the radius of the discharge current from the bearing 390 r is radial distance from center of the at least one spark

The spark radius is determined by

ER 0.5

r4ati

tan -1

Kp ⁰ · ⁵ R ²

Where

R is the radius of the discharge current of the bearing 390 a is the thermal diffusivity

t is the on time of the at least one spark

K is the thermal conductivity

E ₀ is the energy density

The thermal module 326 is further configured to determine lo cation of the at least one spark based on the distribution of the spark heat and the spark radius .

The defect module 330 is configured to generate a defect model to determine a defect in the bearing 390 based on the bearing model. As used herein, the term "defect profile" refers to anomalous data represented as a function of operation environ ment, operation profile and/or load profile associated with the bearing and/or technical system. The defect in the bearing 390 may include erosion of bearing raceway due to the dis charge current. The defect module 330 includes defect profile module 332. The defect profile module 332 is configured to generate the defect profiles based on the distribution of the spark heat and the spark radius .

In an embodiment, the network interface 350 is a cloud inter face with a cloud computing platform 352. The cloud computing platform 352 include a profile generator module. The profile generator is configured to generate predetermined defect pro files based on the bearing specification and the technical specification. The predetermined defect profiles are used by the defect profile module 332 to validate the defect profiles generated based on the spark heat and the spark radius . The validated defect profiles are used to determine the defect in the bearing 390.

In an embodiment, the defect profile module 332 is configured to generate an erosion pattern based on the spark heat and the spark radius. The erosion pattern is indicative of the defect such as defect type, defect location, defect severity, etc.

The life module 340 is configured to determine the remaining life of the bearing 390 based on the defect. The life module 340 is configured to predict a defect propagation based on lo cation of the defect and type of the defect. The life module 340 is configured to estimate an expended life of the bearing 390 based on the bearing model. The remaining life is estimat ed based on the expended life.

The expended life, the remaining life and a usage profile of the bearing are rendered on the display 306 via the GUI 308. The GUI 308 is configured to interactively render a degrada tion view of the bearing 390 and/or the technical system 380 based on the bearing model. The degradation view depicts a re al-time degradation and a predicted degradation of the bearing 390 or the technical system 380.

FIG 4 illustrates a system 400 to manage one or more technical systems 482, 484, 486, 488 with one or more bearings 482A, 484A, 486A and 488A according an embodiment of the present in vention. The technical systems 482, 484, 486, 488 are located in separate facilities 480 and 485. Example facility may be a complex industrial set-up such as a power plant, wind farm, power grid, manufacturing facility, process plants and so on.

The system 400 includes a server 405, a network interface 450 communicatively coupled to the server 405. The system 400 also includes the apparatus 300 communicatively coupled to the technical systems 482, 484, 486, 488 and the server 405 via the network interface 450. The operation of the apparatus 300 is in accordance with the above description. The server 405 includes a communication unit 402, one or more processing units 404 and a memory 410. The memory 410 includes a bearing database 412 and a system database 414. The memory 410 is configured to store computer program instructions de fined by modules, for example, a profile generator module 416 and a design module 418. In an embodiment, server 405 can also be implemented on a cloud computing environment, where compu ting resources are delivered as a service over the network 450.

As used herein, "cloud computing environment" refers to a pro cessing environment comprising configurable computing physical and logical resources, for example, networks, servers, stor age, applications, services, etc., and data distributed over the network 450, for example, the internet. The cloud compu ting environment provides on-demand network access to a shared pool of the configurable computing physical and logical re sources. The network 450 is, for example, a wired network, a wireless network, a communication network, or a network formed from any combination of these networks.

The bearing database 412 is a repository of bearing specifica tion of the bearing 482A and a fleet of the bearing (for exam ple bearings 484A, 486A and 488A including 482A) . The system database 414 is a repository of technical specification of the technical system 482 and a fleet of the technical system (for example, technical systems 484, 486, 488).

The profile generator module 416 is configured to generate de fect profiles based on the bearing specification and the tech nical specification. The defect profiles are updated based on the defect detected in the bearing 482A in real-time. The de sign module 418 determines whether the defect is recurrent in the fleet of bearings. If the defect is recurrent, design for the fleet of bearings is optimized to mitigate the defect.

The system 400 is also includes third party maintenance center 490 that can provide service and maintenance to the technical systems 482, 484, 486, 488. The maintenance center 490 is de- termined such that the availability and reliability of the technical systems 482, 484, 486, 488 is ensured.

FIG 5 illustrates a system for determining remaining life of a bearing in a technical system, according to an embodiment of the present invention. The system includes an apparatus 500 associated with the bearing. The system also includes a cloud computing platform 550 including defect module 552 and an ana lyzer module 554. The system also includes a user device 590 accessible to a user via a GUI 592.

The apparatus 500 performs the steps 502-522 to determine the remaining useful life of the bearing. At step 502, a thermal model of the bearing is generated based on a bearing specifi cation and a technical specification. At step 504 an erosion pattern is determined based on the thermal model. At step 506, the erosion pattern is validated based on predetermined defect profiles generated by the defect module 552. Further, at step 506, remaining life of the erosion pattern is determined based on the predetermined defect profiles.

The defect module 552 is configured to generate the defect profiles based on historical condition data of the bearing. The defect module 552 received analysed historical condition data of the bearing and a fleet of the bearings from the ana lyser module 554. The analyser module 554 includes a learning algorithm using one of supervised learning technique and unsu pervised learning technique to automatically determine defects in the historical condition data. The defects in the histori cal condition data are used to generate the defect profiles by the defect module 552.

At step 508, operation parameters such as vibration frequency and vibration amplitude are analysed to evaluate impact on the erosion pattern. At step 510, characteristics of the erosion pattern are determined based on the vibration frequency and the vibration amplitude. Further, at step 512 a current model is generated based on condition data associated with the operation of the bearing and the technical system. At step 514, vibration data from the condition data is used to generate a real-time defect pattern. At step 516, the real-time defect pattern is mapped to the erosion pattern. At step 518, the erosion pattern is tuned to converge with the real-time defect pattern. The tuning of the real-time defect pattern is performed to modify the remaining life of the erosion pattern in accordance with the condition data .

At step 520, the real-time defect pattern rendered on the GUI 592 to indicate a defect in a bearing raceway. At step 522, the remaining life and expended life are rendered in real-time on the GUI 592.

FIG 6 illustrates a method for determining remaining life of a bearing, according to an embodiment of the present invention. The method begins at step 602 by receiving condition data as sociated with the operation of the bearing and a technical system housing the bearing. The condition data of the bear ing/technical system is received from different sources (e.g., sensors, scanners, user devices, etc.). The sensors measure operating parameters associated with the technical system. The sensors may include vibration sensors, current and voltage sensors, etc. For example, measurement of shaft voltage in a motor is mapped to an operation parameter of the bearing. The term "operation parameter" refers to one or more characteris tics of the bearing. Accordingly, the condition data is a measure of the operating parameters associated with the opera tion of the bearing. For example, the condition data includes values of vibration, temperature, current, magnetic flux, ve locity, power of the motor including the bearing.

At step 604, a voltage model of the bearing is generated based on the condition data. The condition data includes bearing load and bearing speed. In an embodiment, the bearing load and bearing speed is mapped with respect to breakdown voltage of the bearing and a common mode voltage of the bearing. In an- other embodiment, the bearing load and bearing speed are mapped in a graphical programming environment . The advantage of mapping the bearing load and bearing speed enables model ling, simulation and analysis of multidomain dynamical sys tems .

At step 606, a current model of the bearing is generated based on the voltage model, the bearing specification and the tech nical specification. The current model maps the breakdown voltage and the common mode voltage to discharge current. For example, the bearing specification includes bearing dimen sions, bearing size, bearing lubrication, lubrication thick ness, bearing operating temperature, bearing interfaces, etc. The technical specification includes technical system type, technical system load, technical system speed, technical sys tem orientation, etc.

At step 608, a thermal model is generated based on the current model. As used herein, the thermal model is a representation of the spark heat and the spark diameter. The thermal model maps the spark heat and the spark diameter to the discharge current. In an embodiment, the thermal model includes distri bution of the spark heat and the spark diameter in time se ries .

At step 610, a defect model is generated based on the thermal model. The defect model includes defects that are detected in the condition data. At step 610, the condition data is com pared with defect profiles to predict the defects. As used herein, the term "defect profile" refers to anomalous data represented as a function of operation environment, operation profile and/or load profile associated with the bearing and/or technical system.

The defect profiles are generated based on the bearing speci fication and the technical specification. The defect in the bearing may also be predicted based on the comparison between the condition data and with predetermined defect profiles. At step 612, location of the defects is determined based on the defect profile and the condition data. For example, at step 612 location of at least one spark in the bearing is de termined. The location of spark may be determined in the bear ing raceway.

At step 614, remaining life of the bearing is predicted based on the predicted defect and the location of the defect. Fur ther, a defect propagation based on location of the defect and type of the defect. Further, the remaining life of the bearing based on the predicted defect propagation. As used herein, the remaining life refers to life of the bearing with and without the detected defect. The remaining life includes remaining useful life (RUL) , down-time, maintenance time, etc.

The present invention can take a form of a computer program product comprising program modules accessible from computer- usable or computer-readable medium storing program code for use by or in connection with one or more computers, proces sors, or instruction execution system. For the purpose of this description, a computer-usable or computer-readable medium can be any apparatus that can contain, store, communicate, propa gate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The medium can be electronic, magnetic, optical, electromag netic, infrared, or semiconductor system (or apparatus or de vice) or a propagation mediums in and of themselves as signal carriers are not included in the definition of physical com puter-readable medium include a semiconductor or solid state memory, magnetic tape, a removable computer diskette, random access memory (RAM) , a read only memory (ROM) , a rigid magnet ic disk and optical disk such as compact disk read-only memory (CD-ROM), compact disk read/write, and DVD. Both processors and program code for implementing each aspect of the technolo gy can be centralized or distributed (or a combination there of) as known to those skilled in the art.

While the present invention has been described in detail with reference to certain embodiments, it should be appreciated that the present invention is not limited to those embodi ments. In view of the present disclosure, many modifications and variations would be present themselves, to those skilled in the art without departing from the scope of the various em- bodiments of the present invention, as described herein. The scope of the present invention is, therefore, indicated by the following claims rather than by the foregoing description.